TAO Dino training pipeline

Please provide the following information when requesting support.
• Network Type Dino

• Training spec file(If have, please share here)

train:
  num_gpus: 1
  num_nodes: 1
  validation_interval: 1
  optim:
    lr_backbone: 2e-05
    lr: 2e-4
    lr_steps: [11]
    momentum: 0.9
  num_epochs: 12
  precision: fp16
  checkpoint_interval: 1
  activation_checkpoint: True
  pretrained_model_path: /workspace/tao-experiments/dino/dino_fan_large_imagenet22k_36ep.pth
dataset:
  train_data_sources:
    - image_dir: /data/images/train/
      json_file: /data/train/annotations.json
  val_data_sources:
    - image_dir: /data/images/valid/
      json_file: /data/valid/annotations.json
  test_data_sources:
    image_dir: /data/images/test/
    json_file: /data/test/annotations.json
  num_classes: 6
  batch_size: 8
  workers: 2
  augmentation:
    fixed_padding: True
model:
  backbone: fan_large
  train_backbone: False
  num_feature_levels: 4
  dec_layers: 6
  enc_layers: 6
  num_queries: 900
  num_select: 100
  dropout_ratio: 0.0
  dim_feedforward: 2048

I have used above training spec file configuration , eventhough i have added the test dataset i didn’t see the result of the model prediction on the test set in any of the tensorboard graphs or i didn’t see any stats as the model prediction was performed after training on the test dataset

Then what should be the use of that dataset

Please guide me

Could you find the log file under result folder?
Refer to the link.

For visualizing images during training, it is not supported yet in DINO.
After training, user can run inference to get the visualized images.

Only log file is the lightning_logs file

which only contains the checkpoint and all , i didn’t see the results of the test set i have provided

The trainer.test is called in evaluate.py according to the link.
So you can run tao model dino evaluate xxx to get the evaluation metrics result.

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.